Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7353. Min Range: -6.7353
Max Act: 6.7353. Min Act: -0.1700
Data Index: 4751101 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7353. Min Range: -6.7353
Max Act: 6.4853. Min Act: -0.1700
Data Index: 4380430 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7353. Min Range: -6.7353
Max Act: 6.3603. Min Act: -0.1700
Data Index: 6989759 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7353. Min Range: -6.7353
Max Act: 6.1728. Min Act: -0.1700
Data Index: 586370 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7353. Min Range: -6.7353
Max Act: 6.1416. Min Act: -0.1700
Data Index: 7236232 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7353. Min Range: -6.7353
Max Act: 6.1416. Min Act: -0.1700
Data Index: 1545736 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7353. Min Range: -6.7353
Max Act: 6.0166. Min Act: -0.1700
Data Index: 7373994 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.9853. Min Act: -0.1700
Data Index: 3292044 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.9853. Min Act: -0.1700
Data Index: 4521847 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.8291. Min Act: -0.1700
Data Index: 2976685 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.8291. Min Act: -0.1700
Data Index: 3285394 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7978. Min Act: -0.1700
Data Index: 7874594 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7978. Min Act: -0.1700
Data Index: 5367583 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7978. Min Act: -0.1700
Data Index: 469937 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7666. Min Act: -0.1700
Data Index: 7109392 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7666. Min Act: -0.1700
Data Index: 3443505 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7353. Min Act: -0.1700
Data Index: 727830 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7041. Min Act: -0.1700
Data Index: 3568883 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7041. Min Act: -0.1700
Data Index: 3210241 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7353. Min Range: -6.7353
Max Act: 5.7041. Min Act: -0.1700
Data Index: 5376817 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19